View in EDS

Quality-aware blind image motion deblurring.

Saved in:
Bibliographic Details
Title: Quality-aware blind image motion deblurring.
Authors: Song, Tianshu1 (AUTHOR), Li, Leida1,2 (AUTHOR) ldli@xidian.edu.cn, Wu, Jinjian2 (AUTHOR), Dong, Weisheng2 (AUTHOR), Cheng, Deqiang1 (AUTHOR)
Source: Pattern Recognition. Sep2024, Vol. 153, pN.PAG-N.PAG. 1p.
Subjects: Prior learning, Generalization
Abstract: Recent mapping-based motion deblurring methods lack the regularization of prior knowledge, resulting in an over-reliance on the training data and limited generalization ability. As deblurring aims to improve image quality, we quantitatively analyze and further discover the strong correlation between image quality and sharpness. Motivated by the above facts and notable accomplishments of recent no-reference image quality assessment (NR-IQA), we present a novel framework that incorporates quality knowledge into mapping-based deblurring models. Specifically, we extract quality-aware features from NR-IQA models as prior knowledge, and subsequently propose a prediction-based strategy and an encoder-reuse strategy to integrate knowledge into the encoder and decoder, respectively. After training, the model can simultaneously deblur images and predict quality features, indicating that it has grasped the knowledge and validating the effectiveness of the proposed embedding strategies. Extensive experimental results show that embedding quality knowledge consistently improves model performance and the model achieves state-of-the-art intra/cross-dataset results. Code and pre-trained models are available at https://github.com/esnthere/QAMD. • Integrating no-reference image quality assessment into image deblurring. • Prediction-based strategy for encoder knowledge embedding. • Encoder-reuse strategy for decoder knowledge embedding. • Simultaneously deblurring images and predicting quality features. • SOTA intra/cross-dataset test performance. [ABSTRACT FROM AUTHOR]
Copyright of Pattern Recognition is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 177421868
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Quality-aware blind image motion deblurring.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Song%2C+Tianshu%22">Song, Tianshu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Leida%22">Li, Leida</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> ldli@xidian.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wu%2C+Jinjian%22">Wu, Jinjian</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Dong%2C+Weisheng%22">Dong, Weisheng</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Cheng%2C+Deqiang%22">Cheng, Deqiang</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Pattern+Recognition%22">Pattern Recognition</searchLink>. Sep2024, Vol. 153, pN.PAG-N.PAG. 1p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Prior+learning%22">Prior learning</searchLink><br /><searchLink fieldCode="DE" term="%22Generalization%22">Generalization</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Recent mapping-based motion deblurring methods lack the regularization of prior knowledge, resulting in an over-reliance on the training data and limited generalization ability. As deblurring aims to improve image quality, we quantitatively analyze and further discover the strong correlation between image quality and sharpness. Motivated by the above facts and notable accomplishments of recent no-reference image quality assessment (NR-IQA), we present a novel framework that incorporates quality knowledge into mapping-based deblurring models. Specifically, we extract quality-aware features from NR-IQA models as prior knowledge, and subsequently propose a prediction-based strategy and an encoder-reuse strategy to integrate knowledge into the encoder and decoder, respectively. After training, the model can simultaneously deblur images and predict quality features, indicating that it has grasped the knowledge and validating the effectiveness of the proposed embedding strategies. Extensive experimental results show that embedding quality knowledge consistently improves model performance and the model achieves state-of-the-art intra/cross-dataset results. Code and pre-trained models are available at https://github.com/esnthere/QAMD. • Integrating no-reference image quality assessment into image deblurring. • Prediction-based strategy for encoder knowledge embedding. • Encoder-reuse strategy for decoder knowledge embedding. • Simultaneously deblurring images and predicting quality features. • SOTA intra/cross-dataset test performance. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Pattern Recognition is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=177421868
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.patcog.2024.110568
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: N.PAG
    Subjects:
      – SubjectFull: Prior learning
        Type: general
      – SubjectFull: Generalization
        Type: general
    Titles:
      – TitleFull: Quality-aware blind image motion deblurring.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Song, Tianshu
      – PersonEntity:
          Name:
            NameFull: Li, Leida
      – PersonEntity:
          Name:
            NameFull: Wu, Jinjian
      – PersonEntity:
          Name:
            NameFull: Dong, Weisheng
      – PersonEntity:
          Name:
            NameFull: Cheng, Deqiang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Text: Sep2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 00313203
          Numbering:
            – Type: volume
              Value: 153
          Titles:
            – TitleFull: Pattern Recognition
              Type: main
ResultId 1